1 code implementation • 27 Jun 2023 • Louis Fouquet, Simona Maggio, Léo Dreyfus-Schmidt
In our experiments, we compare TLogME to state-of-the-art metrics in the estimation of transfer performance of the Faster-RCNN object detector.
no code implementations • 27 Jul 2022 • Victor Bouvier, Simona Maggio, Alexandre Abraham, Léo Dreyfus-Schmidt
If Uncertainty Quantification (UQ) is crucial to achieve trustworthy Machine Learning (ML), most UQ methods suffer from disparate and inconsistent evaluation protocols.
1 code implementation • 21 Jun 2022 • Simona Maggio, Victor Bouvier, Léo Dreyfus-Schmidt
ML models deployed in production often have to face unknown domain changes, fundamentally different from their training settings.
2 code implementations • 3 Sep 2021 • Alexandre Abraham, Léo Dreyfus-Schmidt
This work explores the effect of noisy sample selection in active learning strategies.
no code implementations • 28 Jun 2021 • Simona Maggio, Léo Dreyfus-Schmidt
The term dataset shift refers to the situation where the data used to train a machine learning model is different from where the model operates.
no code implementations • 18 Dec 2020 • Alexandre Abraham, Léo Dreyfus-Schmidt
Active Learning (AL) is an active domain of research, but is seldom used in the industry despite the pressing needs.